SIENTIAPDE-1174

Update replica count in values.yaml, add application status metrics in metrics.py, and implement Prometheus server in worker.py for enhanced observability.
This commit is contained in:
vitor-aignosi
2025-07-31 13:01:39 -03:00
parent 2efad30304
commit 7925b8a2ae
3 changed files with 28 additions and 2 deletions

View File

@@ -1,5 +1,11 @@
from prometheus_client import Gauge, Counter
APP_UP = Gauge(
"app_up",
"Indicates if the application is running (1) or shutting down (0)",
["pod_id"],
)
CORE_LABELS = ["pod_id", "model_name", "pipeline_name"]
LABORIOUS_DATA_WRITTEN_COUNT = Counter(